Search
107 articles for “mean square error”
-
House Price Estimation Using Linear Regression: A Machine Learning Perspective
Abstract: House price prediction plays a crucial role in the real estate industry, helping buyers, sellers, and investors make well-informed decisions. Accurate estimation of property values enables stakeholders to assess market trends, plan investments, and minimize financial risks. This study focuses on the application of linear regression, a fundamental and widely used machine learning algorithm, to predict house prices based on multiple influencing factors. These factors include location, property size, number …
Published in Research & Reviews : Journal of Statistics · Vol. 15, Issue 1, 2026 · pp. 21–29 Read article
-
Image Super Resolution Using Back-Projection based on Canny Edge Detection and Gabor Filter Prior
Abstract: In recent years, due to the advancement of mixed media instrumentation and machine gadgets, single-image super resolution has currently been converted into a thought subject. Super-resolution is the procedure of improving a high-resolution image from varied low-resolution pictures of a similar scene. The key goal of super-resolution imaging is to reproduce a higher-resolution image focused around a group of pictures, procured from a similar scene and indicated as “low-resolution” pictures, …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 2, Issue 3, 2015 · pp. 48–56 Read article
-
Intercomparison of Parameter Estimation Methods of EVI Distribution for Rainfall Frequency Analysis
Abstract: For planning, design and management of civil and hydraulic structures, estimation of extreme rainfall for a given return period is considered as one of the important parameters. This can be achieved through Extreme Value Analysis (EVA) by fitting of Extreme Value Type-I (EVI) distribution to the observed data. In this paper, a comparative study on determination of parameters of EVI distribution by eight different methods such as graphical method, method …
Published in Journal of Water Resource Engineering and Management · Vol. 7, Issue 3, 2020 · pp. 1–13 Read article
-
Graph Sampling by Spanning Tree under Stratified Setup
Abstract: The sampling theory and its methodologies are based on assumption that the population under survey is of individuals and respondents have provided the answer of questions asked. When population is of graphical structure like containing nodes and edge links then it is complicated to apply the usual sampling procedures. Spanning tree is specified type of a graph, which is always connected with all nodes and becomes a sub-graph. Assume that …
Published in Research & Reviews : Journal of Statistics · Vol. 5, Issue 2, 2016 · pp. 11–31 Read article
-
Managing the Resources of LTE Networks using Multi-orthogonal Access based on Deep Learning
Abstract: AbstractOne of the topics discussed in telecommunications systems is joint subcarrier and power allocation in the uplink of an NOMA system that we study. Due to this reason a novel radio resource management framework is presented based on code-domain and a deep learning algorithm for uplink and downlink transmissions, such that the neural network is trained by Bayesian regularization back propagation and the mean squared error )MSE) are the training …
Published in Journal of Telecommunication, Switching Systems and Networks · Vol. 7, Issue 2, 2020 · pp. 19–26 Read article
-
Indoor Localization of Mobile Device Using Fingerprinting Technique
Abstract: AbstractIndoor localization technology is real-time tracking of any device or person in an indoor area via a control device. In this paper, the fingerprinting method is utilized to track mobile devices in a specific indoor area. Fingerprinting, also known as pattern matching or database correlation method (DCM), needs a powerful received signal strength indication (RSSI) database which helps to make signal strength maps as well as used for matching. The …
Published in Recent Trends in Electronics Communication Systems · Vol. 4, Issue 3, 2017 · pp. 1–8 Read article
-
Signature Based Human Behaviour Prediction
Abstract: Earlier personality or behavior of a person was predicted by spending lot of time with the person. As we know, spending time with person is very difficult task. Concerning this problem, in the present study a method has been proposed for the behavioral prediction of a person through signature analysis. The prediction is done from four features which are alignment, thickness, shape and pen pressure as found in individual’s signature. …
Published in Recent Trends in Programming languages · Vol. 2, Issue 2, 2015 · pp. 13–21 Read article
-
Estimation of Stratospheric Ozone Concentration over Southern Nigeria using Neural Network: Case Study of Lagos and Port Harcourt
Abstract: The neural network model was developed to estimate the stratospheric ozone concentrations along with some meteorological parameters. The neural network was trained using monthly maximum data provided by Nigerian Meteorological Agency (NIMET) and National Aeronautics and Space Administration (NASA) over a period of 43year (1970-2012) in the towns of Lagos and Port Harcourt Ozone concentration from the two stations was estimated using a surface meteorological variable as predictors for the …
Published in Research & Reviews : Journal of Space Science & Technology · Vol. 8, Issue 1, 2019 · pp. 4–9 Read article
-
Intercomparison of Rainfall Estimates of Probability Distributions for Developing the Intensity-Duration-Frequency Curves
Abstract: Determination of short duration rainfall through the developed Intensity-Duration-Frequency (IDF) curve is of utmost importance for planning, design, operation and management of civil and hydraulic structures. For which, extreme value analysis (EVA) of rainfall that consists of fitting probability distributions such as Normal, Log Normal (LN2), Pearson Type-3, Log Pearson Type-3, Extreme Value Type-1 (EV1) and Generalized Extreme Value (GEV) to the annual 1-day maximum rainfall series is carried out. …
Published in Journal of Water Resource Engineering and Management · Vol. 9, Issue 3, 2022 · pp. 39–53 Read article
-
Single Sensor Camera Image Denoising Using PCA and Demosaicking with LMMSE
Abstract: Single sensor cameras are used mostly for image acquisition in digital cameras with a colour filter array (CFA). These cameras save image in an unrefined format, since the complete process of image acquisition get lengthy and complex, so it introduces noise in the image and hence requires some efficient technique for denoising. Different techniques have been used to denoise the captured image but efficiency of the algorithms has not been …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 3, Issue 2, 2016 · pp. 1–10 Read article
-
The Role of Adaptive Filters in Enhancing Acoustic Echo Cancellation Efficiency in Noisy Environments
Abstract: The novel approach that this work discusses is a DCD-based iterative learning filter approach improved with deep learning methodologies, designed to improve the efficiency of acoustic echo cancellation. The proposed system can really manage both linear and nonlinear echo scenarios, dynamically adapting to fluctuating acoustic environments. The above comparative evaluations with standard filter, the standard RLS filter, indicate that the mean square error, and the standard deviation of the correlation …
Published in International Journal of Radio Frequency Innovations · Vol. 2, Issue 2, 2024 · pp. 9–24 Read article
-
Forecasting Maize Price using Exponential Smoothing Method
Abstract: Maize is emerging as third most important crop after rice and wheat in India. A better understanding of maize price situation and future prices will facilitate farmers and end users to make appropriate decisions regarding buying and selling patterns; hence government should make adequate policies. Exponential smoothing method is appropriate tool in time series analysis. Forecast of maize price can be done by using simple exponential smoothing method. The forecasted …
Published in Research & Reviews : Journal of Statistics · Vol. 7, Issue 1, 2018 · pp. 91s–95s Read article
-
Predictive Modeling and Optimization of Tensile and Flexural Strength in FDM 3D Printing Using Decision Trees and Bayesian Optimization.
Abstract: This research investigates predictive modelling and optimization technique for the tensile and flexural strength of PlA (Poly Lactic Acid) in Fused Deposition Modelling (FDM) 3D printing. Employing Decision Trees and Bayesian Optimization enhances comprehension and control of 3D printing process. Precise model predicts PLA material properties based on input parameters. Methodology involves rigorous data preprocessing, encompassing, cleaning, transformation, and normalization. Hyperparameter optimization via grid search systematically explores configurations, optimizing model …
Published in Journal of Polymer & Composites · Vol. 11, Issue 12, 2023 · pp. 203–214 Read article
-
A Gamified Digital Platform for Sustainable Farming Practices: Simulation, Statistical Analysis, and Water Resource Management Implications
Abstract: Sustainable farming practices play a critical role in enhancing agricultural water use efficiency, conserving limited water resources, and ensuring long-term food security under increasing environmental and climatic pressures. Despite their importance, farmer participation in conventional agricultural extension and training programs remains limited due to low engagement and a lack of sustained motivation. To address this challenge, this study proposes a gamified digital decision-support platform aimed at promoting sustainable agricultural and …
Published in Journal of Water Resource Engineering and Management · Vol. 13, Issue 1, 2026 · pp. 13–24 Read article
-
Smart Framework for Personal Fuel Expense Tracking and Carbon Emission Assessment
Abstract: This study presents a smart system that is intended to assist individuals and administrators in tracking their fuel costs and keeping an eye on their daily carbon emissions. It makes it simpler to make decisions by examining fuel consumption and its effects on the environment. The technology gathers real-time emissions data from vehicles equipped with Internet of Things devices. It can predict future trends of emissions by utilizing AI-based predictive …
Published in Journal of Thermal Engineering and Applications · Vol. 11, Issue 3, 2024 · pp. 36–44 Read article
-
Achieving Multi-objectives Using a Single Neural Network
Abstract: Achieving multi-objectives using a single neural network is a research area that aims to develop techniques to optimize multiple objectives simultaneously using a single neural network. This approach can be applied in various fields, such as image and speech recognition, robotics, and natural language processing, to achieve better performance and reduce the complexity of the models. The key challenge in this area is to balance the trade-off between different objectives …
Published in Research & Reviews: Discrete Mathematical Structures · Vol. 9, Issue 3, 2022 · pp. 1–15 Read article
-
Machine Learning Approach to Predict the Performability and Emissions of Diesel Engine Fueled with Doped Biodiesel Blend
Abstract: Enhancing the performability and emission characteristics of diesel engines has been a difficult task in light of growing concerns about global warming and other negative effects, as diesel accounts for 70% of global energy demand. In this study, engine performance and exhaust emissions for various fuel blends were thoroughly evaluated using machine learning techniques to predict engine emission and performance behavior. We focused on biodiesel blend and nanoparticle additive concentration …
Published in International Journal of Mechanical Dynamics and Systems Analysis · Vol. 3, Issue 1, 2025 · pp. 1–12 Read article
-
Study of an Improved Quantum Particle Swarm Optimization-Based Framework for Neural Network Optimization in Modelling of Polymer Data
Abstract: The accurate forecasting of polymer viscosity at various physicochemical conditions has been quite critical due to the nonlinear interactions and interrelations between the variables. This paper suggests a better hybrid modelling framework, which involves the use of Artificial Neural Networks (ANN) and more advanced versions of Quantum Particle Swarm Optimization (QPSO) to better predict polymer viscosity. The input parameters taken are, namely, log (shear rate), polymer concentration, NaCl concentration, Ca …
Published in Journal of Polymer & Composites · Vol. 14, Issue 4, 2026 · pp. 282–297 Read article
-
Machine Learning Approach to Determine Corrosion Potential of Friction Stir Welded Joints
Abstract: The main objective of the research study is to create an Artificial Neural Network (ANN) architecture to predict corrosion resistance from the Friction Stir Welding experimental dataset given to us. This is also to find the mean squared error and mean absolute percentage error of the given model which will help to analyze the losses and efficiency of the model. In the Artificial Neural Architecture, Tool Rotational Speed (rpm), Axial …
Published in Journal of Image Processing & Pattern Recognition Progress · Vol. 7, Issue 1, 2020 · pp. 5–17 Read article
-
Deep Learning Enhanced Compressive Sensing for Wireless IoT Data Optimization and Weather Monitoring.
Abstract: This research explores the application of deep learning and compressive sensing in order to optimize data traffic in non-orthogonal multiple access (NOMA)-based wireless internet of things (IoT) networks and weather monitoring. Such a framework would be very effective and overcome pilot attacks and reconstruction losses for secure data transmission. In this regard, a strong communication model has been adopted based on power-domain NOMA for simultaneous wireless transmission by multiple IoT …
Published in International Journal of Satellite Remote Sensing · Vol. 2, Issue 2, 2024 · pp. 20–36 Read article